Optimal-Point Variance Reduction For Bayesian Optimization With Regret Guarantee

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Takeno, Shion
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913176683020288
author Takeno, Shion
author_facet Takeno, Shion
contents This paper studies a one-step lookahead Bayesian optimization (BO) method and its theoretical guarantee. Although the empirical effectiveness of one-step lookahead BO methods, such as entropy search, has been studied extensively, they often rely on computationally intractable approximations, and their regret guarantees remain underdeveloped. Thus, this paper proposes a one-step lookahead BO method called optimal-point variance reduction (OVR), which requires only posterior sampling and Monte Carlo approximations. We obtain a uniform error bound over an input domain for the Monte Carlo estimation in OVR. Furthermore, we show that the regularized OVR, with the slight modification to promote exploration, achieves a vanishing Bayesian expected simple regret upper bound. Finally, we demonstrate the effectiveness of OVR through numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00956
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Optimal-Point Variance Reduction For Bayesian Optimization With Regret Guarantee
Takeno, Shion
Machine Learning
This paper studies a one-step lookahead Bayesian optimization (BO) method and its theoretical guarantee. Although the empirical effectiveness of one-step lookahead BO methods, such as entropy search, has been studied extensively, they often rely on computationally intractable approximations, and their regret guarantees remain underdeveloped. Thus, this paper proposes a one-step lookahead BO method called optimal-point variance reduction (OVR), which requires only posterior sampling and Monte Carlo approximations. We obtain a uniform error bound over an input domain for the Monte Carlo estimation in OVR. Furthermore, we show that the regularized OVR, with the slight modification to promote exploration, achieves a vanishing Bayesian expected simple regret upper bound. Finally, we demonstrate the effectiveness of OVR through numerical experiments.
title Optimal-Point Variance Reduction For Bayesian Optimization With Regret Guarantee
topic Machine Learning
url https://arxiv.org/abs/2606.00956